It has been estimated that over a billion people are using or learning English as a second or foreign language, and the numbers are growing not only for English but for other languages as well. These language learners provide a burgeoning market for tools that help identify and correct learners' writing errors. Unfortunately, the errors targeted by typical commercial proofreading tools do not include those aspects of a second language that are hardest to learn. This volume describes the types of constructions English language learners find most difficult: constructions containing prepositions, articles, and collocations. It provides an overview of the automated approaches that have been developed to identify and correct these and other classes of learner errors in a number of languages.
Error annotation and system evaluation are particularly important topics in grammatical error detection because there are no commonly accepted standards. Chapters in the book describe the options available to researchers, recommend best practices for reporting results, and present annotation and evaluation schemes.
The final chapters explore recent innovative work that opens new directions for research. It is the authors' hope that this volume will continue to contribute to the growing interest in grammatical error detection by encouraging researchers to take a closer look at the field and its many challenging problems.
Table of Contents
Special Problems of Language Learners
Evaluating Error Detection Systems
Data-Driven Approaches to Articles and Prepositions
Different Errors and Different Approaches
Annotating Learner Errors
About the Author(s)Claudia Leacock
, CTB McGraw-Hill
Claudia Leacock is a Research Scientist III at CTB McGraw-Hill where she works on methods for automated scoring. Previously, as a consultant with the Butler Hill Group, she collaborated with the Microsoft Research team that developed ESL Assistant, a web-based prototype tool for detecting and correcting grammatical errors of English language learners. As a Distinguished Member of Technical Staff at Pearson Knowledge Technologies (2004-2007), and previously as a Principal Development Scientist at Educational Testing Service (1997-2004), she developed tools for both automated assessment of short-answer content-based questions and grammatical error detection and correction. As a member of the WordNet group at Princeton University's Cognitive Science Lab (1991-1997), her research focused on word sense disambiguation. Dr. Leacock received a B.A. in English from NYU, a Ph.D. in linguistics from the City University of New York, Graduate Center, and was a post-doctoral fellow at IBM, T.J. Watson Research Center.Martin Chodorow
, Hunter College and the Graduate Center, City University of New York
Martin Chodorow received his Ph.D. in cognitive psychology (psycholinguistics) from MIT. Following a two-year postdoctoral position in computational linguistics at IBM's Thomas Watson Research Center, he joined the faculty of Hunter College and the Graduate School of the City University of New York, where he is Professor of Psychology & Linguistics. His NLP research interests include measurement of text similarity and automated assessment of writing. He has served as a consultant for IBM, Princeton University's Cognitive Science Laboratory, and, for the past 16 years, Educational Testing Service, where he works on the grammatical error detection system in ETS's e-rater essay scoring engine and Criterion Online Writing Service. His current research in cognitive psychology examines the psychological processes that underlie proofreading.Michael Gamon
, Microsoft Research
Michael Gamon is a researcher in the Natural Language Processing Group at Microsoft Research. He joined Microsoft Research after receiving his Ph.D. in linguistics from the University of Washington in 1996. He worked first on developing the German computational grammar which is used in the Word grammar checker and became interested in the specific problems of language learners at that time. Subsequently he has done research in a number of areas, from natural language generation to sentiment detection, language in social media, and query classification. In the past several years he has been working on the Microsoft Research ESL Assistant, a prototype web service for detection and correction of grammatical errors of English language learners. His current interests include more flexible data-driven algorithms for grammatical error detection.Joel Tetreault
, Yahoo! Labs
Joel Tetreault is Senior Research Scientist at Yahoo! Labs in New York City. His research focus is Natural Language Processing with specific interests in anaphora, dialogue and discourse processing, machine learning, and applying these techniques to the analysis of English language learning and automated essay scoring. Previously he was Principal Manager of the Core Natural Language group at Nuance Communications, Inc., where he worked on the research and development of NLP tools and components for the next generation of intelligent dialogue systems. Prior to Nuance, he worked at Educational Testing Service for six years as a managing research scientist where he researched automated methods for detecting grammatical errors by non-native speakers, plagiarism detection, and content scoring. Tetreault received his B.A. in Computer Science from Harvard University (1998) and his M.S. and Ph.D. in Computer Science from the University of Rochester (2004). He was also a postdoctoral research scientist at the University of Pittsburgh's Learning Research and Development Center (2004-2007), where he worked on developing spoken dialogue tutoring systems.
The second edition of Automated Grammatical Error Detection for Language Learners provides exactly what the title promises, covering the state-of-the-art for grammatical error detection and correction for learner language data, with particular emphasis on English prepositions and articles...the book summarizes system design, gold standard annotation to support the task, and issues surrounding the evaluation of correction systems...Given the topics of the book, especially that of annotation, researchers working with learner corpora, and especially on the annotation of such corpora, can benefit greatly from reading this volume.Markus Dickinson, Indiana University (in International Journal of Learner Corpus Research 1:2, 2015)